By arthurgailes
Opinionated R skills: collapse, mapgl, flextable, r-ai for fast data ops, interactive maps, LLM integration, and skill creation
Use when code loads ellmer, btw, mcptools, ragnar, or vitals, building LLM-powered R applications, implementing RAG workflows, or choosing between R AI packages (meta-skill for ellmer/btw/mcptools/ragnar/vitals)
Use when code loads or uses btw (library(btw), btw::), providing R session context to LLMs, registering tools for ellmer chat, or copying R object descriptions to clipboard
Use when code loads or uses collapse (library(collapse), collapse::), performing fast grouped or weighted statistics in R, or seeking faster alternatives to dplyr aggregation
Use when code loads or uses duckplyr (library(duckplyr), duckplyr::), processing large datasets with dplyr syntax, working with Parquet files in R, or needing lazy evaluation for bigger-than-memory data
Use when code loads or uses duckspatial (library(duckspatial), duckspatial::), performing spatial joins or areal interpolation on large vector datasets in R, or needing faster spatial operations than sf
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.

AI agents don't know every R package. When they encounter unfamiliar ones, they hallucinate APIs or fall back to verbose base R.
This plugin teaches them.
Generate a skill from any R package:
/r-package-skill collapse
Pulls documentation from CRAN, extracts patterns, writes a skill file. Your agent now knows when to use collapse, which functions matter, and how they compose.
Works for any package—CRAN, GitHub, internal tools. Each skill is tested, graded, and optimized before deployment.
/plugin marketplace add arthurgailes/r-package-skills
/plugin install r-package-skills@r-package-skills
Fetch and follow instructions from https://raw.githubusercontent.com/arthurgailes/r-package-skills/main/.codex/INSTALL.md
Fetch and follow instructions from https://raw.githubusercontent.com/arthurgailes/r-package-skills/main/.opencode/INSTALL.md
Generate your first skill:
/r-package-skill data.table
You'll be asked where to install (Personal, Project, or Custom path). Then the agent:
SKILL.md addressing failuresTakes 10-12 minutes with 3-4 approval prompts. Skill appears at your chosen path, ready to use.
This plugin focuses on newer and lesser-known R packages — not the popular ones AI models already know well.
For example:
The goal: fill knowledge gaps, not duplicate existing training. We include packages where agents consistently struggle or hallucinate without guidance.
You decide what matters. Use /r-package-skill to generate skills for:
We won't ship 1,000 packages — just curated skills for packages that demonstrate the pattern and solve common problems. The generator is the real product; the included skills are examples and starting points.
| Skill | Description |
|---|---|
| r-package-skill | Generate a skill from any R package documentation |
| Skill | Focus |
|---|---|
| r-ai | R AI ecosystem navigation and integration patterns |
| r-mapping | R mapping workflow guidance (freestiler + mapgl) |
| Skill | Focus |
|---|---|
| r-ellmer | Chat with LLMs, multi-provider support (hub package) |
| r-btw | Provide R context (docs, data) to LLMs |
| r-mcptools | Let AI agents execute R code in live sessions |
| r-ragnar | RAG workflows, vector stores, document search |
| r-vitals | LLM output evaluation and quality testing |
| Skill | Focus |
|---|---|
| r-collapse | Fast grouped/weighted stats, panel data transformations |
| r-duckplyr | Lazy evaluation for large datasets with DuckDB backend |
npx claudepluginhub arthurgailes/r-package-skills --plugin r-package-skillsModern R development skills for Claude Code - tidyverse patterns, rlang metaprogramming, Bayesian inference, performance optimization, and more
Collection of skills for Shiny app development
Multi-agent workflow framework for building, testing, and shipping statistical software packages
361 agentic skills across 65 domains, 72 agent personas, and 17 team compositions following the agentskills.io open standard
Self-documenting, self-improving framework for analytical repositories
Integrated Rust development skills for multiple domains (UI, Robotics, etc.)